Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/leemysw/feishu-docx/agents-mdgit clone --depth 1 https://github.com/leemysw/feishu-docxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/leemysw/feishu-docx/agents-md)<a href="https://agentmods.dev/instructions/leemysw/feishu-docx/agents-md"><img src="https://agentmods.dev/badge/instructions/leemysw/feishu-docx/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00558 | $0.00558 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
feishu-docx AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Source lives under feishu_docx/, with subpackages for auth/ (OAuth), core/ (API + parsing), schema/ (Pydantic models), cli/ (Typer commands), tui/ (Textual UI), and utils/ (config/temp helpers). Tests are in tests/ with test_*.py files and sample outputs under tests/output/. User-facing docs and assets live in docs/ (e.g., screenshots). The CLI entry point is exposed via the feishu-docx script, with main.py as a local runner.
Build, Test, and Development Commands
Use editable installs for development and keep Python 3.11+.
pip install -e ".[dev]" # install dev deps (pytest/ruff/mypy)
pytest tests/ -v # run the test suite
feishu-docx --help # list CLI commands
Packaging uses Hatchling; build artifacts with python -m build (see pyproject.toml). The Makefile contains a release upload target (make upload) for maintainers.
Coding Style & Naming Conventions
Follow standard Python conventions: 4-space indentation, snake_case for functions/variables, PascalCase for classes, and type hints where practical. Static checks use Ruff and MyPy. Ruff is configured for line-length = 120 and ignores E501; prefer Ruff fixes over manual formatting. Keep modules focused on a single responsibility (e.g., CLI wiring stays in feishu_docx/cli).
Testing Guidelines
Tests run with pytest. Name new tests as tests/test_<area>.py and keep fixtures close to the modules they validate. When adding new CLI behavior, include at least one test in tests/test_cli.py.
Commit & Pull Request Guidelines
Recent history uses short, imperative subjects with conventional prefixes like fix: or emoji tags such as :sparkles: and :recycle:. Keep titles concise and scoped to one change. PRs should include a clear description, test results (commands run), and links to related issues or tickets. Add screenshots for TUI/CLI output changes when relevant.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 28 lines · 558 tokens per session scan A 30cf96653fb3
feishu-docx AGENTS.md is an instructions file published in the GitHub repository leemysw/feishu-docx (252 stars, last pushed 1mo ago), licensed MIT. It adds 558 tokens to every session, about $0.0028 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ratel AGENTS.md
AGENTS.md instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).
colin CLAUDE.md
Claude Code instructions for PrefectHQ/colin, covering colin development guidelines, required development workflow, documentation requirements, user-facing documentation (docs/) and docs/architecture.md.
colin AGENTS.md
AGENTS.md instructions for PrefectHQ/colin, a project described as: A context engine that treats skills as software.
ratel CLAUDE.md
Claude Code instructions for ratel-ai/ratel, a project described as: Context engineering for AI agents. 80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
sentry-instrumentation AGENTS.md
Instructions for tortastudios/sentry-instrumentation, covering agents guide — sentry-instrumentation, what this repo is, this repo has no "skill registry", if you're a codex agent asked to install this skill and skill-enable block (copy into consumer agents.md).